INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

1,048,576

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

doGet

-0.40

得

-0.37

Etymology

-0.37

 fascination

-0.37

pe

-0.37

toggle

-0.36

 lower

-0.36

bus

-0.35

picasso

-0.35

 hegemony

-0.35

POSITIVE LOGITS

saraba

0.93

__(/*!

0.91

principalTable

0.90

 gynhyrchwyd

0.86

AddTagHelper

0.80

 ویکی‌پدیا

0.79

findpost

0.79

Искәрмәләр

0.75

 CreateTagHelper

0.73

 متعلقه

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.